Search Results for author:
Found 281 papers, 91 papers with code
Correlative Multi-Label Multi-Instance Image Annotation
The cross-level label coherence en-codes the consistency between the labels at the image leveland the labels at the region level.
AgeNet: Deeply Learned Regressor and Classifier for Robust Apparent Age Estimation
Another key feature of the proposed AgeNet is that, to avoid the problem of over-fitting on small apparent age training set, we exploit a general-to-specific transfer learning scheme.
Ranked #4 on
Age Estimation
on ChaLearn 2015
Scaling POMDPs For Selecting Sellers in E-markets-Extended Version
In multiagent e-marketplaces, buying agents need to select good sellers by querying other buyers (called advisors).
Leveraging Datasets With Varying Annotations for Face Alignment via Deep Regression Network
Facial landmark detection, as a vital topic in computer vision, has been studied for many decades and lots of datasets have been collected for evaluation.
Occlusion-Free Face Alignment: Deep Regression Networks Coupled With De-Corrupt AutoEncoders
Face alignment or facial landmark detection plays an important role in many computer vision applications, e. g., face recognition, facial expression recognition, face animation, etc.
Seeing the Forest from the Trees in Two Looks: Matrix Sketching by Cascaded Bilateral Sampling
Given a matrix A of size m by n, state-of-the-art randomized algorithms take O(m * n) time and space to obtain its low-rank decomposition.
Large-scale Feature Selection of Risk Genetic Factors for Alzheimer's Disease via Distributed Group Lasso Regression
Then we select the relevant group features by performing the group Lasso feature selection process in a sequence of parameters.
Intensity Video Guided 4D Fusion for Improved Highly Dynamic 3D Reconstruction
The availability of high-speed 3D video sensors has greatly facilitated 3D shape acquisition of dynamic and deformable objects, but high frame rate 3D reconstruction is always degraded by spatial noise and temporal fluctuations.
Multi-task Dictionary Learning based Convolutional Neural Network for Computer aided Diagnosis with Longitudinal Images
Firstly, we pre-train CNN on the ImageNet dataset and transfer the knowledge from the pre-trained model to the medical imaging progression representation, generating the features for different tasks.
Interacting Attention-gated Recurrent Networks for Recommendation
In particular, we propose a novel attention scheme to learn the attention scores of user and item history in an interacting way, thus to account for the dependencies between user and item dynamics in shaping user-item interactions.
Hourly-Similarity Based Solar Forecasting Using Multi-Model Machine Learning Blending
The final optimal model is a combination of MMFF models with the best-performed blending algorithm at every hour.
An Unsupervised Clustering-Based Short-Term Solar Forecasting Methodology Using Multi-Model Machine Learning Blending
This methodology consists of three parts: GHI time series unsupervised clustering, pattern recognition, and UC-based forecasting.
Inference Aided Reinforcement Learning for Incentive Mechanism Design in Crowdsourcing
Incentive mechanisms for crowdsourcing are designed to incentivize financially self-interested workers to generate and report high-quality labels.
Dynamically Hierarchy Revolution: DirNet for Compressing Recurrent Neural Network on Mobile Devices
Recurrent neural networks (RNNs) achieve cutting-edge performance on a variety of problems.
Spectral Network Embedding: A Fast and Scalable Method via Sparsity
In this paper, we propose a $10\times \sim 100\times$ faster network embedding method, called Progle, by elegantly utilizing the sparsity property of online networks and spectral analysis.
An Operation Network for Abstractive Sentence Compression
Delete-based models have the strong ability to delete undesired words, while generate-based models are able to reorder or rephrase the words, which are more coherent to human sentence compression.
Geometric Constrained Joint Lane Segmentation and Lane Boundary Detection
The main contributions of the proposed frame- work are highlighted in two facets: (1) We put forward a multiple-task learning framework with mutually interlinked sub-structures between lane segmentation and lane boundary detection to improve overall performance.
Semi-supervised Learning on Graphs with Generative Adversarial Nets
We first provide insights on working principles of adversarial learning over graphs and then present GraphSGAN, a novel approach to semi-supervised learning on graphs.
Reinforcement Learning based Dynamic Model Selection for Short-Term Load Forecasting
The optimal DMS policy is applied to select the best model at each time step with a moving window.
MICIK: MIning Cross-Layer Inherent Similarity Knowledge for Deep Model Compression
State-of-the-art deep model compression methods exploit the low-rank approximation and sparsity pruning to remove redundant parameters from a learned hidden layer.
Generative Visual Dialogue System via Adaptive Reasoning and Weighted Likelihood Estimation
The key challenge of generative Visual Dialogue (VD) systems is to respond to human queries with informative answers in natural and contiguous conversation flow.
Class-incremental Learning via Deep Model Consolidation
The idea is to first train a separate model only for the new classes, and then combine the two individual models trained on data of two distinct set of classes (old classes and new classes) via a novel double distillation training objective.
Regularize, Expand and Compress: Multi-task based Lifelong Learning via NonExpansive AutoML
Lifelong learning, the problem of continual learning where tasks arrive in sequence, has been lately attracting more attention in the computer vision community.
Multi-Normal Estimation via Pair Consistency Voting
This paper presents a unified definition for point cloud normals of feature and non-feature points, which allows feature points to possess multiple normals.
Average-case Analysis of the Assignment Problem with Independent Preferences
Recently, [Deng, Gao, Zhang 2017] show that when the agents' preferences are drawn from a uniform distribution, its \textit{average-case approximation ratio} is upper bounded by 3. 718.
Transferrable Operative Difficulty Assessment in Robot-assisted Teleoperation: A Domain Adaptation Approach
Providing an accurate and efficient assessment of operative difficulty is important for designing robot-assisted teleoperation interfaces that are easy and natural for human operators to use.
Imbalanced Learning-based Automatic SAR Images Change Detection by Morphologically Supervised PCA-Net
Change detection is a quite challenging task due to the imbalance between unchanged and changed class.
Method of diagnosing heart disease based on deep learning ECG signal
Some have tried to combine expertise and signal processing to classify ECG signal by heart disease type.
FocusNet: Imbalanced Large and Small Organ Segmentation with an End-to-End Deep Neural Network for Head and Neck CT Images
In this paper, we propose an end-to-end deep neural network for solving the problem of imbalanced large and small organ segmentation in head and neck (HaN) CT images.
Video Affective Effects Prediction with Multi-modal Fusion and Shot-Long Temporal Context
We select the most suitable modalities for valence and arousal tasks respectively and each modal feature is extracted using the modality-specific pre-trained deep model on large generic dataset.
Self-supervised Scale Equivariant Network for Weakly Supervised Semantic Segmentation
This regularized CAM can be embedded in most recent advanced weakly supervised semantic segmentation framework.
Research Commentary on Recommendations with Side Information: A Survey and Research Directions
This Research Commentary aims to provide a comprehensive and systematic survey of the recent research on recommender systems with side information.
Diagonal Graph Convolutional Networks with Adaptive Neighborhood Aggregation
In this paper, we revisit the mathematical foundation of GCNs and study how to extend their representation capacity.
VIDEO AFFECTIVE IMPACT PREDICTION WITH MULTIMODAL FUSION AND LONG-SHORT TEMPORAL CONTEXT
Feature extraction, multi-modal fusion and temporal context fusion are crucial stages for predicting valence and arousal values in the emotional impact, but have not been successfully exploited.
Hierarchical Attentive Knowledge Graph Embedding for Personalized Recommendation
Knowledge graphs (KGs) have proven to be effective for high-quality recommendation, where the connectivities between users and items provide rich and complementary information to user-item interactions.
Bilinear Constraint based ADMM for Mixed Poisson-Gaussian Noise Removal
In this paper, we propose new operator-splitting algorithms for the total variation regularized infimal convolution (TV-IC) model [4] in order to remove mixed Poisson-Gaussian(MPG) noise.
Which Channel to Ask My Question? Personalized Customer Service RequestStream Routing using DeepReinforcement Learning
These observations suggest that our proposed method can seek the trade-off where both channel resources and customers' satisfaction are optimal.
Learning Improvement Heuristics for Solving Routing Problems
In this paper, we propose a deep reinforcement learning framework to learn the improvement heuristics for routing problems.
COBRA: Context-aware Bernoulli Neural Networks for Reputation Assessment
Trust and reputation management (TRM) plays an increasingly important role in large-scale online environments such as multi-agent systems (MAS) and the Internet of Things (IoT).
Learning Variable Ordering Heuristics for Solving Constraint Satisfaction Problems
In this paper, we propose a deep reinforcement learning based approach to automatically discover new variable ordering heuristics that are better adapted for a given class of CSP instances.
Bounded Incentives in Manipulating the Probabilistic Serial Rule
In this paper, we characterize the extent to which an individual agent can increase its utility by strategic manipulation.
Model Watermarking for Image Processing Networks
In this way, when the attacker trains one surrogate model by using the input-output pairs of the target model, the hidden watermark will be learned and extracted afterward.
Multiform Fonts-to-Fonts Translation via Style and Content Disentangled Representations of Chinese Character
The main purpose of this paper is to design a network framework that can extract and recombine the content and style of the characters.
Application of Structural Similarity Analysis of Visually Salient Areas and Hierarchical Clustering in the Screening of Similar Wireless Capsule Endoscopic Images
Small intestinal capsule endoscopy is the mainstream method for inspecting small intestinal lesions, but a single small intestinal capsule endoscopy will produce 60, 000 - 120, 000 images, the majority of which are similar and have no diagnostic value.
STAN-CT: Standardizing CT Image using Generative Adversarial Network
Computed tomography (CT) plays an important role in lung malignancy diagnostics and therapy assessment and facilitating precision medicine delivery.
Self-supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentation
Our method is based on the observation that equivariance is an implicit constraint in fully supervised semantic segmentation, whose pixel-level labels take the same spatial transformation as the input images during data augmentation.
Data Augmentation
Weakly supervised Semantic Segmentation
+1
Reconstructing normal section profiles of 3D revolving structures via pose-unconstrained multi-line structured-light vision
First, we establish a model to estimate the axis of 3D revolving geometrical structure and the normal section profile using corresponding points.
Single-Side Domain Generalization for Face Anti-Spoofing
In this work, we propose an end-to-end single-side domain generalization framework (SSDG) to improve the generalization ability of face anti-spoofing.
Adaptive Structural Fingerprints for Graph Attention Networks
Yet, how to fully exploit rich structural information in the attention mechanism remains a challenge.
Estimation of the Laser Frequency Nosie Spectrum by Continuous Dynamical Decoupling
Decoherence induced by the laser frequency noise is one of the most important obstacles in the quantum information processing.
Quantum Physics
Benchmarking High Bandwidth Memory on FPGAs
FPGAs are starting to be enhanced with High Bandwidth Memory (HBM) as a way to reduce the memory bandwidth bottleneck encountered in some applications and to give the FPGA more capacity to deal with application state.
Hardware Architecture
Graph Random Neural Network for Semi-Supervised Learning on Graphs
We study the problem of semi-supervised learning on graphs, for which graph neural networks (GNNs) have been extensively explored.
A Convolutional Neural Network with Parallel Multi-Scale Spatial Pooling to Detect Temporal Changes in SAR Images
Furthermore, to verify the generalization of the proposed method, we apply our proposed method to the cross-dataset bitemporal SAR image change detection, where the MSSP network (MSSP-Net) is trained on a dataset and then applied to an unknown testing dataset.
A Re-visit of the Popularity Baseline in Recommender Systems
On the widely used MovieLens dataset, we show that the performance of popularity could be significantly improved by 70% or more, if we consider the popular items at the time point when a user interacts with the system.
Active Sampling for Min-Max Fairness
We propose simple active sampling and reweighting strategies for optimizing min-max fairness that can be applied to any classification or regression model learned via loss minimization.
Federated Mutual Learning
The experiments show that FML can achieve better performance than alternatives in typical FL setting, and clients can be benefited from FML with different models and tasks.
Structural Landmarking and Interaction Modelling: on Resolution Dilemmas in Graph Classification
Graph neural networks are promising architecture for learning and inference with graph-structured data.
Wireless Performance Evaluation of Building Layouts: Closed-Form Computation of Figures of Merit
This paper presents a part of our ground-breaking work on evaluation of buildings in terms of wireless friendliness in the building-design stage.
Attentive Fusion Enhanced Audio-Visual Encoding for Transformer Based Robust Speech Recognition
The proposed method can sufficiently combine the two streams and weaken the over-reliance on the audio modality.
FrUITeR: A Framework for Evaluating UI Test Reuse
UI testing is tedious and time-consuming due to the manual effort required.
Software Engineering
Low-Rank Reorganization via Proportional Hazards Non-negative Matrix Factorization Unveils Survival Associated Gene Clusters
Towards the goal of precision health and cancer treatments, the proposed algorithm can help understand and interpret high-dimensional heterogeneous genomics data with accurate identification of survival-associated gene clusters.
Cascaded Semantic and Positional Self-Attention Network for Document Classification
In this work, we propose a new architecture to aggregate the two sources of information using cascaded semantic and positional self-attention network (CSPAN) in the context of document classification.
Low-frequency whistler waves excited by relativistic laser pulses
It is shown by multi-dimensional particle-in-cell simulations that intense secondary whistler waves with special vortex-like field topology can be excited by a relativistic laser pulse in the highly magnetized, near-critical density plasma.
Plasma Physics
A Critical Study on Data Leakage in Recommender System Offline Evaluation
To evaluate recommendation systems in a realistic manner in offline setting, we propose a timeline scheme, which calls for a revisit of the recommendation model design.
Learning to Dispatch for Job Shop Scheduling via Deep Reinforcement Learning
Priority dispatching rule (PDR) is widely used for solving real-world Job-shop scheduling problem (JSSP).
Passport-aware Normalization for Deep Model Protection
Only when the model IP is suspected to be stolen by someone, the private passport-aware branch is added back for ownership verification.
Diversify Question Generation with Continuous Content Selectors and Question Type Modeling
However, question generation is actually a one-to-many problem, as it is possible to raise questions with different focuses on contexts and various means of expression.
Digital Twins: State of the Art Theory and Practice, Challenges, and Open Research Questions
This work explores the various DT features and current approaches, the shortcomings and reasons behind the delay in the implementation and adoption of digital twin.
Delayed Feedback Modeling for the Entire Space Conversion Rate Prediction
In this paper, we propose a novel neural network framework ESDF to tackle the above three challenges simultaneously.
Graph Random Neural Networks for Semi-Supervised Learning on Graphs
We study the problem of semi-supervised learning on graphs, for which graph neural networks (GNNs) have been extensively explored.
Data Augmentation for Multiclass Utterance Classification -- A Systematic Study
Utterance classification is a key component in many conversational systems.
Attributes Aware Face Generation with Generative Adversarial Networks
Recent studies have shown remarkable success in face image generations.
Multi-Decoder Attention Model with Embedding Glimpse for Solving Vehicle Routing Problems
We present a novel deep reinforcement learning method to learn construction heuristics for vehicle routing problems.
Multiclass Spinal Cord Tumor Segmentation on MRI with Deep Learning
To the best of our knowledge, this is the first fully automatic deep learning model for spinal cord tumor segmentation.
TGCN: Time Domain Graph Convolutional Network for Multiple Objects Tracking
Multiple object tracking is to give each object an id in the video.
Optical manipulation of electronic dimensionality in a quantum material
Exotic phenomenon can be achieved in quantum materials by confining electronic states into two dimensions.
Strongly Correlated Electrons Materials Science Superconductivity
BridgeDPI: A Novel Graph Neural Network for Predicting Drug-Protein Interactions
Therefore, we hope to develop a novel supervised learning method to learn the PPAs and DDAs effectively and thereby improve the prediction performance of the specific task of DPI.
An Improvement for Quantum Tunneling Radiation of Fermions in a Stationary Kerr-Newman Black Hole Spacetime
By introducing a specific etheric-like vector in the Dirac equation with Lorentz Invariance Violation (LIV) in the curved spacetime, an improved method for quantum tunneling radiation of fermions is proposed.
General Relativity and Quantum Cosmology High Energy Physics - Theory
Spin and polarization effects on the nonlinear Breit-Wheeler pair production in laser-plasma interaction
The spin effect of electrons/positrons ($e^-$/$e^+$) and polarization effect of $\gamma$ photons are investigated in the interaction of two counter-propagating linearly polarized 10-PW-class laser pulses with a thin foil target.
Plasma Physics
Meta-Path-Free Representation Learning on Heterogeneous Networks
To the best of our knowledge, this is the first attempt to break out of the confinement of meta-paths for representation learning on heterogeneous networks.
Spatio-Temporal Multi-step Prediction of Influenza Outbreaks
We compared the MAPEs of SVM, RF, LSTM models of predicting flu data of the 1-4 weeks ahead with and without other countries' flu data.
Dynamic Virtual Graph Significance Networks for Predicting Influenza
In this study, we develop a novel method, Dynamic Virtual Graph Significance Networks (DVGSN), which can supervisedly and dynamically learn from similar "infection situations" in historical timepoints.
M6: A Chinese Multimodal Pretrainer
In this work, we construct the largest dataset for multimodal pretraining in Chinese, which consists of over 1. 9TB images and 292GB texts that cover a wide range of domains.
Deep Model Intellectual Property Protection via Deep Watermarking
By jointly training the target model and watermark embedding, the extra barrier can even be absorbed into the target model.
FocusNetv2: Imbalanced Large and Small Organ Segmentation with Adversarial Shape Constraint for Head and Neck CT Images
Radiotherapy is a treatment where radiation is used to eliminate cancer cells.
Reversible Watermarking in Deep Convolutional Neural Networks for Integrity Authentication
Specifically, we present the reversible watermarking problem of deep convolutional neural networks and utilize the pruning theory of model compression technology to construct a host sequence used for embedding watermarking information by histogram shift.
HINet: Half Instance Normalization Network for Image Restoration
Specifically, we present a novel block: Half Instance Normalization Block (HIN Block), to boost the performance of image restoration networks.
Ranked #3 on
Single Image Deraining
on Test2800
M6-T: Exploring Sparse Expert Models and Beyond
Mixture-of-Experts (MoE) models can achieve promising results with outrageous large amount of parameters but constant computation cost, and thus it has become a trend in model scaling.
MFR 2021: Masked Face Recognition Competition
These teams successfully submitted 18 valid solutions.
From Personalized Medicine to Population Health: A Survey of mHealth Sensing Techniques
Mobile Sensing Apps have been widely used as a practical approach to collect behavioral and health-related information from individuals and provide timely intervention to promote health and well-beings, such as mental health and chronic cares.
CT Image Harmonization for Enhancing Radiomics Studies
While remarkable advances have been made in Computed Tomography (CT), capturing CT images with non-standardized protocols causes low reproducibility regarding radiomic features, forming a barrier on CT image analysis in a large scale.
SelfCF: A Simple Framework for Self-supervised Collaborative Filtering
Collaborative filtering (CF) is widely used to learn informative latent representations of users and items from observed interactions.
Impact of Rotary-Wing UAV Wobbling on Millimeter-wave Air-to-Ground Wireless Channel
Our contributions of this paper lie in: i) modeling the wobbling process of a hovering RW UAV; ii) developing an analytical model to derive the channel temporal autocorrelation function (ACF) for the millimeter-wave RW UAV A2G link in a closed-form expression; and iii) investigating how RW UAV wobbling impacts the Doppler effect on the millimeter-wave RW UAV A2G link.
Supply Chain Digital Twin Framework Design: An Approach of Supply Chain Operations Reference Model and System of Systems
This paper explains what is 'twined' in supply chain digital twin and how to 'twin' them to handle the spatio-temporal dynamic issue.
Locality-aware Channel-wise Dropout for Occluded Face Recognition
Furthermore, by randomly dropping out several feature channels, our method can well simulate the occlusion of larger area.
Exploring Structure Consistency for Deep Model Watermarking
However, little attention has been devoted to the protection of DNNs in image processing tasks.
Poison Ink: Robust and Invisible Backdoor Attack
As the image structure can keep its semantic meaning during the data transformation, such trigger pattern is inherently robust to data transformations.
Meta Gradient Adversarial Attack
In recent years, research on adversarial attacks has become a hot spot.
Optimisation of two-stage biomass gasification for hydrogen production via artificial neural network
The developed neural network model was then applied for optimising operating conditions of the two-stage gasification for high carbon conversion, high hydrogen yield and low carbon dioxide in nitrogen and carbon dioxide environments.
LUAI Challenge 2021 on Learning to Understand Aerial Images
This report summarizes the results of Learning to Understand Aerial Images (LUAI) 2021 challenge held on ICCV 2021, which focuses on object detection and semantic segmentation in aerial images.
Pairwise Emotional Relationship Recognition in Drama Videos: Dataset and Benchmark
We expect the ERATO as well as our proposed SMTA to open up a new way for PERR task in video understanding and further improve the research of multi-modal fusion methodology.
Learning Scenario Representation for Solving Two-stage Stochastic Integer Programs
Many practical combinatorial optimization problems under uncertainty can be modeled as stochastic integer programs (SIPs), which are extremely challenging to solve due to the high complexity.
Generative Adversarial Training for Neural Combinatorial Optimization Models
Recent studies show that deep neural networks can be trained to learn good heuristics for various Combinatorial Optimization Problems (COPs).
ACDC: Online Unsupervised Cross-Domain Adaptation
We consider the problem of online unsupervised cross-domain adaptation, where two independent but related data streams with different feature spaces -- a fully labeled source stream and an unlabeled target stream -- are learned together.
Deep Reinforcement Learning for Solving the Heterogeneous Capacitated Vehicle Routing Problem
To solve those problems, we propose a DRL method based on the attention mechanism with a vehicle selection decoder accounting for the heterogeneous fleet constraint and a node selection decoder accounting for the route construction, which learns to construct a solution by automatically selecting both a vehicle and a node for this vehicle at each step.
Heterogeneous Attentions for Solving Pickup and Delivery Problem via Deep Reinforcement Learning
In particular, the heterogeneous attention mechanism specifically prescribes attentions for each role of the nodes while taking into account the precedence constraint, i. e., the pickup node must precede the pairing delivery node.
M6-10T: A Sharing-Delinking Paradigm for Efficient Multi-Trillion Parameter Pretraining
Recent expeditious developments in deep learning algorithms, distributed training, and even hardware design for large models have enabled training extreme-scale models, say GPT-3 and Switch Transformer possessing hundreds of billions or even trillions of parameters.
MGC: A Complex-Valued Graph Convolutional Network for Directed Graphs
We test our model on several graph datasets including directed homogeneous and heterogeneous graphs.
NeuroLKH: Combining Deep Learning Model with Lin-Kernighan-Helsgaun Heuristic for Solving the Traveling Salesman Problem
We present NeuroLKH, a novel algorithm that combines deep learning with the strong traditional heuristic Lin-Kernighan-Helsgaun (LKH) for solving Traveling Salesman Problem.
Cross-Vendor CT Image Data Harmonization Using CVH-CT
We propose a novel deep learning approach called CVH-CT for harmonizing CT images captured using scanners from different vendors.
SenseMag: Enabling Low-Cost Traffic Monitoring using Non-invasive Magnetic Sensing
Extensive experiment based on real-word field deployment (on the highways in Shenzhen, China) shows that SenseMag significantly outperforms the existing methods in both classification accuracy and the granularity of vehicle types (i. e., 7 types by SenseMag versus 4 types by the existing work in comparisons).
A Novel Sequence Tagging Framework for Consumer Event-Cause Extraction
To this end, we introduce a fresh perspective to revisit the relational event-cause extraction task and propose a novel sequence tagging framework, instead of extracting event types and events-causes separately.
Learning Large Neighborhood Search Policy for Integer Programming
We then design a neural network to learn policies for each variable in parallel, trained by a customized actor-critic algorithm.
Parameterized Knowledge Transfer for Personalized Federated Learning
To deal with such model constraints, we exploit the potentials of heterogeneous model settings and propose a novel training framework to employ personalized models for different clients.
Learning an Adaptive Meta Model-Generator for Incrementally Updating Recommender Systems
Recommender Systems (RSs) in real-world applications often deal with billions of user interactions daily.
3D Lip Event Detection via Interframe Motion Divergence at Multiple Temporal Resolutions
We define a motion divergence measure using 3D lip landmarks to quantify the interframe dynamics of a 3D speaking lip.
Adaptive Image Transformations for Transfer-based Adversarial Attack
Adversarial attacks provide a good way to study the robustness of deep learning models.
Adaptive Perturbation for Adversarial Attack
Instead of using the sign function, we propose to directly utilize the exact gradient direction with a scaling factor for generating adversarial perturbations, which improves the attack success rates of adversarial examples even with fewer perturbations.
Deep Auto-encoder with Neural Response
In this study, we propose an integrated framework called Deep Autoencoder with Neural Response (DAE-NR), which incorporates information from ANN and the visual cortex to achieve better image reconstruction performance and higher neural representation similarity between biological and artificial neurons.
Tracing Text Provenance via Context-Aware Lexical Substitution
Tracing text provenance can help claim the ownership of text content or identify the malicious users who distribute misleading content like machine-generated fake news.
GIMIRec: Global Interaction Information Aware Multi-Interest Framework for Sequential Recommendation
Sequential recommendation based on multi-interest framework models the user's recent interaction sequence into multiple different interest vectors, since a single low-dimensional vector cannot fully represent the diversity of user interests.
From Deterioration to Acceleration: A Calibration Approach to Rehabilitating Step Asynchronism in Federated Optimization
In the setting of federated optimization, where a global model is aggregated periodically, step asynchronism occurs when participants conduct model training by efficiently utilizing their computational resources.
Initiative Defense against Facial Manipulation
To this end, we first imitate the target manipulation model with a surrogate model, and then devise a poison perturbation generator to obtain the desired venom.
DENSE: Data-Free One-Shot Federated Learning
One-shot Federated Learning (FL) has recently emerged as a promising approach, which allows the central server to learn a model in a single communication round.
Towards Efficient Data Free Black-Box Adversarial Attack
The proposed method can efficiently imitate the target model through a small number of queries and achieve high attack success rate.
Enhancing Face Recognition With Self-Supervised 3D Reconstruction
In this paper, we propose to enhance face recognition with a bypass of self-supervised 3D reconstruction, which enforces the neural backbone to focus on the identity-related depth and albedo information while neglects the identity-irrelevant pose and illumination information.
FedDTG:Federated Data-Free Knowledge Distillation via Three-Player Generative Adversarial Networks
This technique mitigates the user heterogeneity problem and better protects user privacy.
Supervised and Self-supervised Pretraining Based COVID-19 Detection Using Acoustic Breathing/Cough/Speech Signals
By using the acoustic signals to train the network, respectively, we can build individual models for three tasks, whose parameters are averaged to obtain an average model, which is then used as the initialization for the BiLSTM model training of each task.
A Noise-Robust Self-supervised Pre-training Model Based Speech Representation Learning for Automatic Speech Recognition
In this work, we therefore first analyze the noise robustness of wav2vec2. 0 via experiments.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Adversarial Examples for Good: Adversarial Examples Guided Imbalanced Learning
Adversarial examples are inputs for machine learning models that have been designed by attackers to cause the model to make mistakes.
A Coalition Formation Game Approach for Personalized Federated Learning
Facing the challenge of statistical diversity in client local data distribution, personalized federated learning (PFL) has become a growing research hotspot.
Learning to Solve Routing Problems via Distributionally Robust Optimization
Recent deep models for solving routing problems always assume a single distribution of nodes for training, which severely impairs their cross-distribution generalization ability.
Learning Contextually Fused Audio-visual Representations for Audio-visual Speech Recognition
The proposed approach explores both the complementarity of audio-visual modalities and long-term context dependency using a transformer-based fusion module and a flexible masking strategy.
Spectral Graph Clustering for Intentional Islanding Operations in Resilient Hybrid Energy Systems
Establishing cleaner energy generation therefore improving the sustainability of the power system is a crucial task in this century, and one of the key strategies being pursued is to shift the dependence on fossil fuel to renewable technologies such as wind, solar, and nuclear.
Collaborative Intelligent Reflecting Surface Networks with Multi-Agent Reinforcement Learning
Intelligent reflecting surface (IRS) is envisioned to be widely applied in future wireless networks.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
A Complementary Joint Training Approach Using Unpaired Speech and Text for Low-Resource Automatic Speech Recognition
Unpaired data has shown to be beneficial for low-resource automatic speech recognition~(ASR), which can be involved in the design of hybrid models with multi-task training or language model dependent pre-training.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
PICASSO: Unleashing the Potential of GPU-centric Training for Wide-and-deep Recommender Systems
However, we observe that GPU devices in training recommender systems are underutilized, and they cannot attain an expected throughput improvement as what it has achieved in CV and NLP areas.
Do Loyal Users Enjoy Better Recommendations? Understanding Recommender Accuracy from a Time Perspective
Our study offers a different perspective to understand recommender accuracy, and our findings could trigger a revisit of recommender model design.
Adaptive Modulation for Wobbling UAV Air-to-Ground Links in Millimeter-wave Bands
Based on the designed detectors, we propose an adaptive modulation scheme to maximize the average transmission rate under imperfect CSI by optimizing the data transmission time subject to the maximum tolerable BEP.
On Scheduling Mechanisms Beyond the Worst Case
That is, mechanism K is pointwise better than mechanism P. Next, for each task $j$, when machines' execution costs $t_i^j$ are independent and identically drawn from a task-specific distribution $F^j(t)$, we show that the average-case approximation ratio of mechanism K converges to a constant.
Sign Bit is Enough: A Learning Synchronization Framework for Multi-hop All-reduce with Ultimate Compression
Traditional one-bit compressed stochastic gradient descent can not be directly employed in multi-hop all-reduce, a widely adopted distributed training paradigm in network-intensive high-performance computing systems such as public clouds.
Boosting Pruned Networks with Linear Over-parameterization
To address this challenge, we propose a novel method that first linearly over-parameterizes the compact layers in pruned networks to enlarge the number of fine-tuning parameters and then re-parameterizes them to the original layers after fine-tuning.
Snake net and balloon force with a neural network for detecting multiple phases
In order to obtain a physical phase diagram, the snake model with an artificial neural network is applied in an unsupervised learning way by the authors of [Phys. Rev. Lett.
IDEAL: Query-Efficient Data-Free Learning from Black-box Models
Knowledge Distillation (KD) is a typical method for training a lightweight student model with the help of a well-trained teacher model.
Joint Training of Speech Enhancement and Self-supervised Model for Noise-robust ASR
Speech enhancement (SE) is usually required as a front end to improve the speech quality in noisy environments, while the enhanced speech might not be optimal for automatic speech recognition (ASR) systems due to speech distortion.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Sampling Efficient Deep Reinforcement Learning through Preference-Guided Stochastic Exploration
We theoretically prove that the policy improvement theorem holds for the preference-guided $\epsilon$-greedy policy and experimentally show that the inferred action preference distribution aligns with the landscape of corresponding Q-values.
DaisyRec 2.0: Benchmarking Recommendation for Rigorous Evaluation
Recently, one critical issue looms large in the field of recommender systems -- there are no effective benchmarks for rigorous evaluation -- which consequently leads to unreproducible evaluation and unfair comparison.
On the Performance of Data Compression in Clustered Fog Radio Access Networks
The fog-radio-access-network (F-RAN) has been proposed to address the strict latency requirements, which offloads computation tasks generated in user equipments (UEs) to the edge to reduce the processing latency.
Physics-informed Deep Learning for Musculoskeletal Modelling: Predicting Muscle Forces and Joint Kinematics from Surface EMG
At the same time, the physics law between muscle forces and joint kinematics is used the soft constraint.
An IRS Backscatter Enabled Integrated Sensing, Communication and Computation System
This paper proposes to leverage intelligent reflecting surface (IRS) backscatter to realize radio-frequency-chain-free uplink-transmissions (RFCF-UT).
Learning Pseudo Labels for Semi-and-Weakly Supervised Semantic Segmentation
Firstly, we introduce a class-aware cross entropy (CCE) loss for network training.
Microwave QR Code: An IRS-Based Solution
This letter proposes to employ intelligent reflecting surface (IRS) as an information media to display a microwave quick response (QR) code for Internet-of-Things applications.
Multi-modal Transformer Path Prediction for Autonomous Vehicle
To better utilize the lane information, the lanes which are in opposite direction to target agent are not likely to be taken by the target agent and are consequently filtered out.
Hierarchical Compositional Representations for Few-shot Action Recognition
Recently action recognition has received more and more attention for its comprehensive and practical applications in intelligent surveillance and human-computer interaction.
Fed-FSNet: Mitigating Non-I.I.D. Federated Learning via Fuzzy Synthesizing Network
Concretely, we maintain an edge-agnostic hidden model in the cloud server to estimate a less-accurate while direction-aware inversion of the global model.
Federated Learning with Label Distribution Skew via Logits Calibration
Extensive experiments on federated datasets and real-world datasets demonstrate that FedLC leads to a more accurate global model and much improved performance.
A Multi-Channel Next POI Recommendation Framework with Multi-Granularity Check-in Signals
Being equipped with three modules (i. e., global user behavior encoder, local multi-channel encoder, and region-aware weighting strategy), MCMG is capable of capturing both fine- and coarse-grained sequential regularities as well as exploring the dynamic impact of multi-channel by differentiating the region check-in patterns.
Class-Incremental Learning via Knowledge Amalgamation
Catastrophic forgetting has been a significant problem hindering the deployment of deep learning algorithms in the continual learning setting.
Learning to Solve Multiple-TSP with Time Window and Rejections via Deep Reinforcement Learning
We propose a manager-worker framework based on deep reinforcement learning to tackle a hard yet nontrivial variant of Travelling Salesman Problem (TSP), \ie~multiple-vehicle TSP with time window and rejections (mTSPTWR), where customers who cannot be served before the deadline are subject to rejections.
Speech Enhancement Using Self-Supervised Pre-Trained Model and Vector Quantization
Specifically, the encoder and bottleneck layer of the DEMUCS model are initialized using the self-supervised pretrained WavLM model, the convolution in the encoder is replaced by causal convolution, and the transformer encoder in the bottleneck layer is based on causal attention mask.
From Intelligent Agents to Trustworthy Human-Centred Multiagent Systems
The Agents, Interaction and Complexity research group at the University of Southampton has a long track record of research in multiagent systems (MAS).
Robust Data2vec: Noise-robust Speech Representation Learning for ASR by Combining Regression and Improved Contrastive Learning
Self-supervised pre-training methods based on contrastive learning or regression tasks can utilize more unlabeled data to improve the performance of automatic speech recognition (ASR).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
A Comparative Study on Multichannel Speaker-Attributed Automatic Speech Recognition in Multi-party Meetings
Speaker-attributed automatic speech recognition (SA-ASR) in multi-party meeting scenarios is one of the most valuable and challenging ASR task.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Reinforcement Learning Enhanced Weighted Sampling for Accurate Subgraph Counting on Fully Dynamic Graph Streams
Specifically, we propose a weighted sampling algorithm called WSD for estimating the subgraph count in a fully dynamic graph stream, which samples the edges based on their weights that indicate their importance and reflect their properties.
Demystify Self-Attention in Vision Transformers from a Semantic Perspective: Analysis and Application
In contrast, visual data exhibits a fundamentally different structure: Its basic unit (pixel) is a natural low-level representation with significant redundancies in the neighbourhood, which poses obvious challenges to the interpretability of MSA mechanism in ViT.
Feature Correlation-guided Knowledge Transfer for Federated Self-supervised Learning
We prove that FedFoA is a model-agnostic training framework and can be easily compatible with state-of-the-art unsupervised FL methods.
FedTune: A Deep Dive into Efficient Federated Fine-Tuning with Pre-trained Transformers
Federated Learning (FL) is an emerging paradigm that enables distributed users to collaboratively and iteratively train machine learning models without sharing their private data.
Deep Reinforcement Learning Guided Improvement Heuristic for Job Shop Scheduling
Recent studies in using deep reinforcement learning (DRL) to solve Job-shop scheduling problems (JSSP) focus on construction heuristics.
VATLM: Visual-Audio-Text Pre-Training with Unified Masked Prediction for Speech Representation Learning
Although speech is a simple and effective way for humans to communicate with the outside world, a more realistic speech interaction contains multimodal information, e. g., vision, text.
Exploiting Personalized Invariance for Better Out-of-distribution Generalization in Federated Learning
Recently, data heterogeneity among the training datasets on the local clients (a. k. a., Non-IID data) has attracted intense interest in Federated Learning (FL), and many personalized federated learning methods have been proposed to handle it.
Out-of-Distribution Generalization
Personalized Federated Learning
Decision-making with Speculative Opponent Models
To address this issue, we introduce Distributional Opponent-aided Multi-agent Actor-Critic (DOMAC), the first speculative opponent modelling algorithm that relies solely on local information (i. e., the controlled agent's observations, actions, and rewards).
Boosting Personalised Musculoskeletal Modelling with Physics-informed Knowledge Transfer
The salient advantages of the proposed framework are twofold: 1) For the generic model, physics-based domain knowledge is embedded into the loss function of the data-driven model as soft constraints to penalise/regularise the data-driven model.
Ada3Diff: Defending against 3D Adversarial Point Clouds via Adaptive Diffusion
Deep 3D point cloud models are sensitive to adversarial attacks, which poses threats to safety-critical applications such as autonomous driving.
Efficient Stein Variational Inference for Reliable Distribution-lossless Network Pruning
Extensive experiments based on small Cifar-10 and large-scaled ImageNet demonstrate that our method can obtain sparser networks with great generalization performance while providing quantified reliability for the pruned model.
Accelerating Dataset Distillation via Model Augmentation
Dataset Distillation (DD), a newly emerging field, aims at generating much smaller but efficient synthetic training datasets from large ones.
Exploring Optimal Substructure for Out-of-distribution Generalization via Feature-targeted Model Pruning
Recent studies show that even highly biased dense networks contain an unbiased substructure that can achieve better out-of-distribution (OOD) generalization than the original model.
Unveiling Code Pre-Trained Models: Investigating Syntax and Semantics Capacities
These structures are fundamental to understanding code.
Pyramid Dual Domain Injection Network for Pan-sharpening
To this end, we first revisit the degradation process of pan-sharpening in Fourier space, and then devise a Pyramid Dual Domain Injection Pan-sharpening Network upon the above observation by fully exploring and exploiting the distinguished information in both the spatial and frequency domains.
Quantum-Inspired Spectral-Spatial Pyramid Network for Hyperspectral Image Classification
Using QSSN as the building block, we propose an end-to-end quantum-inspired spectral-spatial pyramid network (QSSPN) for HSI feature extraction and classification.
DiffusionCT: Latent Diffusion Model for CT Image Standardization
This work addresses the issue of CT image harmonization using a new diffusion-based model, named DiffusionCT, to standardize CT images acquired from different vendors and protocols.
TAP: Accelerating Large-Scale DNN Training Through Tensor Automatic Parallelisation
However, finding a suitable model parallel schedule for an arbitrary neural network is a non-trivial task due to the exploding search space.
Towards Fairer and More Efficient Federated Learning via Multidimensional Personalized Edge Models
Federated learning (FL) is an emerging technique that trains massive and geographically distributed edge data while maintaining privacy.
Speech Enhancement with Multi-granularity Vector Quantization
With advances in deep learning, neural network based speech enhancement (SE) has developed rapidly in the last decade.
Delving into the Adversarial Robustness of Federated Learning
In this work, we propose a novel algorithm called Decision Boundary based Federated Adversarial Training (DBFAT), which consists of two components (local re-weighting and global regularization) to improve both accuracy and robustness of FL systems.
Pseudo Label-Guided Model Inversion Attack via Conditional Generative Adversarial Network
At first, a top-n selection strategy is proposed to provide pseudo-labels for public data, and use pseudo-labels to guide the training of the cGAN.
Learning Large Neighborhood Search for Vehicle Routing in Airport Ground Handling
Dispatching vehicle fleets to serve flights is a key task in airport ground handling (AGH).
Neural Airport Ground Handling
Airport ground handling (AGH) offers necessary operations to flights during their turnarounds and is of great importance to the efficiency of airport management and the economics of aviation.
TARGET: Federated Class-Continual Learning via Exemplar-Free Distillation
This paper focuses on an under-explored yet important problem: Federated Class-Continual Learning (FCCL), where new classes are dynamically added in federated learning.
Real Face Foundation Representation Learning for Generalized Deepfake Detection
In this study, we propose Real Face Foundation Representation Learning (RFFR), which aims to learn a general representation from large-scale real face datasets and detect potential artifacts outside the distribution of RFFR.
CCLAP: Controllable Chinese Landscape Painting Generation via Latent Diffusion Model
While the style aggregator module is to generate paintings of a style corresponding to a reference image.
Multi-Sample Consensus Driven Unsupervised Normal Estimation for 3D Point Clouds
Comprehensive experiments demonstrate that the two proposed unsupervised methods are noticeably superior to some supervised deep normal estimators on the most common synthetic dataset.
Inhomogeneous graph trend filtering via a l2,0 cardinality penalty
We study estimation of piecewise smooth signals over a graph.
Towards Unbiased Training in Federated Open-world Semi-supervised Learning
Federated Semi-supervised Learning (FedSSL) has emerged as a new paradigm for allowing distributed clients to collaboratively train a machine learning model over scarce labeled data and abundant unlabeled data.
Retraining A Graph-based Recommender with Interests Disentanglement
Then we blend the historical and new preferences in the form of node embeddings in the new graph, through a Disentanglement Module.
Vision Language Pre-training by Contrastive Learning with Cross-Modal Similarity Regulation
Cross-modal contrastive learning in vision language pretraining (VLP) faces the challenge of (partial) false negatives.
A Black-Box Attack on Code Models via Representation Nearest Neighbor Search
Furthermore, the perturbation of adversarial examples introduced by RNNS is smaller compared to the baselines in terms of the number of replaced variables and the change in variable length.
Watermarking Text Generated by Black-Box Language Models
To allow third-parties to autonomously inject watermarks into generated text, we develop a watermarking framework for black-box language model usage scenarios.
BASEN: Time-Domain Brain-Assisted Speech Enhancement Network with Convolutional Cross Attention in Multi-talker Conditions
In this paper, we thus propose a novel time-domain brain-assisted SE network (BASEN) incorporating electroencephalography (EEG) signals recorded from the listener for extracting the target speaker from monaural speech mixtures.
Personalization as a Shortcut for Few-Shot Backdoor Attack against Text-to-Image Diffusion Models
Although recent personalization methods have democratized high-resolution image synthesis by enabling swift concept acquisition with minimal examples and lightweight computation, they also present an exploitable avenue for high accessible backdoor attacks.
CASA-ASR: Context-Aware Speaker-Attributed ASR
In addition, a two-pass decoding strategy is further proposed to fully leverage the contextual modeling ability resulting in a better recognition performance.
